© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1549
    Prev
    Next
    INDEX
    Explanations

    the letter 'w' in various contexts, indicating a focus on its frequency in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ={({
    -0.79
    .";
    -0.75
    "},
    -0.67
    )");
    -0.67
    XXXXX
    -0.67
    ).)
    -0.67
    ).]
    -0.66
    ᾶ
    -0.66
    )');
    -0.65
    :~
    -0.64
    POSITIVE LOGITS
    w
    2.49
     w
    2.27
    𝐰
    1.06
    𝙬
    0.97
    wl
    0.94
     wh
    0.93
    ww
    0.92
    wh
    0.90
    𝑤
    0.89
    𝒘
    0.88
    Activations Density 0.074%

    No Known Activations